NewOpenClips MCP is live.Your AI video studio, inside any AI chat.See how it works →
Back to the gallery
Pricing
Back to the gallery
Paused
0:00/0:00
MiniMax H312s · 16:9

Drag the clip sideways

Up next
Archive Wake

ASSET MAP: @image1 — PERSON_A, present-day, exactly as shown. Photocopy face, hair, skin, age, teal athletic top and gold necklaces from the still. @image2 — the old photograph containing PERSON_B. PERSON_B’s identity, age and appearance come only from that photo. CHARACTER LOCK — HIGHEST PRIORITY: PERSON_A’s face, hairstyle, skin tone, build and apparent age must stay exactly as shown in @image1 throughout. PERSON_B, once animated, must stay exactly the person shown in @image2 — their exact facial features, apparent age (whatever age the photo shows — elderly, do not change it), skin tone, hair and expression range, preserved from the photo. Do not beautify, de-age, age up, or restyle either person. Preserve each person’s gender presentation exactly as shown. No other people enter the scene. Whenever this text and either reference image disagree, follow the image. RESTRAINED PHOTO-WAKING RULE: PERSON_B begins completely still, exactly as printed in @image2 — aged photo texture, tone and grain visible. Their first movements are small and natural only: a soft blink, a faint warm smile, gentle breathing, the smallest head tilt. Do not give PERSON_B fast or large head turns or exaggerated motion before they have fully stepped out of the photo plane — abrupt motion on a photographic likeness distorts the face. Only after they have visibly left the frame do they move naturally and fully. 16:9. TOTAL DURATION: 12 SECONDS. OPENING: already in the room with PERSON_A and the framed print. Never a studio headshot as frame 0. 0-3s: Static establishing shot. PERSON_A stands or sits calmly, holding or seated beside a framed print of the old photo showing PERSON_B — visibly aged, grain, faded tone, slightly worn paper texture. Quiet, still, a little anticipatory. Camera holds completely still. Natural indoor or soft outdoor lighting that makes both PERSON_A and the framed photo look like they belong in the same room. 3-6s: Inside the frame, PERSON_B gently comes to life — a soft blink, a faint warm smile forming, gentle breathing, the smallest natural head tilt. The old photo’s color and depth slowly warm and deepen, the flat printed texture gradually giving way to living dimension, without changing PERSON_B’s identity, age or appearance. PERSON_A notices, their expression shifting to quiet wonder. 6-10s: PERSON_B steps out of the photo’s plane into PERSON_A’s space. They reach out and gently cup PERSON_A’s cheek in one hand, smiling warmly and studying their face as if seeing them for the first time in years. PERSON_A closes their eyes for a moment, leaning slightly into the touch, a small emotional breath escaping. No embrace, no words — just the gesture held for a beat. 10-12s: PERSON_A opens their eyes and meets PERSON_B’s gaze, both smiling softly. Camera slowly pushes in a few inches, or holds steady. CINEMATIC STYLE: Soft natural or warm indoor light, gentle handheld micro-movement, shallow depth of field, live-action realism — preserve real skin texture and imperfections on PERSON_A; PERSON_B’s texture may echo the photo’s grain slightly even once alive, as a subtle visual signature that they came from the photograph. No subtitles. No on-screen text or watermark. Hands have five fingers each, anatomically correct.

3 steps
MiniMax H312s · 16:9
Inspired by Coinis AIon organic

Photoreal cinematic UGC chocolate tasting commercial, warm premium feature-film lighting, glossy, cocoa-brown and golden palette, shallow depth of field, slow-motion mixed with punchy beats, fine film grain, high-end grade. Lead is @image1 (identity locked — exact face, hair and skin from @image1, exactly two hands). HERO PRODUCT — TWO REFERENCES: the wrapped bar's exterior/packaging is exactly @image2 (same wrapper, colour, logo and shape, identical, never changing); the bar's interior/filling is exactly @image3 (its real cross-section — coconut, caramel, nougat, wafer, whatever @image3 actually shows). CRITICAL: never add, invent or imply any filling, ingredient, sauce or drip not visibly present in @image3; if @image3 shows white coconut, the inside is coconut and there is NO caramel. Camera is propped so @image1 has both hands free. 0-3s: @image1 leans toward the propped lens holding the wrapped @image2 bar up to camera, bright inviting reveal, face to lens. 3-7s: @image1 slowly turns the wrapped @image2 bar in warm rim light, extreme macro, wrapper and logo crisp, cocoa dust drifting. 7-11s: @image1 peels the @image2 wrapper back as a ribbon of smooth melting milk chocolate glosses over the bar (chocolate only). 11-15s: @image1 snaps the bar in clean slow-motion to reveal its interior exactly as in @image3 — the real filling — macro and tactile, held toward lens. 15-19s: @image1 takes a bite and gives a genuine satisfied reaction to lens, crisp snap. 19-23s: stylised beauty insert of swirling melted chocolate and only the ingredients actually shown in @image3 orbiting an open piece, premium, not cartoonish, @image1's hand guiding it. 23-27s: hero beat — @image1 presents the wrapped @image2 bar and an open piece showing the @image3 interior together toward lens, wrapper and logo readable. 27-30s: confident final beat holding on @image1 with the @image2 bar, a final glint across the @image2 logo. Let each beat play out fully and finish its action before moving to the next; ONE continuous coherent commercial, smooth motivated transitions, no abrupt cut to an unrelated or random scene mid-action; do not skip or truncate any beat; @image1 identity consistent every shot; exterior always matches @image2 and interior always matches @image3. Realistic food and fluid physics, believable chocolate viscosity, exactly two hands — one holds the bar, the other peels or presents. SOUND: lush warm commercial score, piano-to-orchestral, plus satisfying foley (crisp snap, gentle pour, wrapper rustle, bite); no spoken dialogue, no invented language. Negative: adding caramel, nougat, peanuts, syrup or any filling not present in @image3; the interior differing from @image3; the exterior/wrapper/logo differing from @image2 or changing or duplicating; @image1's identity, face, hair or skin changing; a third hand, extra arm, more than two hands, extra or missing fingers; melty distorted or fake-looking chocolate, plastic textures or plastic skin; cartoonish CGI; on-screen text, captions, subtitles or invented graphics other than the real logo on @image2; watermark; a scene cutting off mid-action; jumping to a random unrelated scene before the current action finishes; skipped or truncated beats; any character or object vanishing, dissolving, fading or teleporting into thin air — every exit is physical.

2 steps
Seedance 2.530s · 9:16
Inspired by obecaon X

An exactly 15-second retro-futurist documentary film, 16:9 horizontal, genuine 1970s archival news footage of a rocket landing — except the rocket is a residential apartment block. Multi-shot, hard cuts. LOOK: aged 16mm colour film. Heavy fine grain, slight gate weave and flicker, faded period colour — washed cyan sky, warm yellowed concrete, muted reds and browns. Soft optics, mild chromatic fringing, occasional dust on the emulsion. Long telephoto, heat shimmer. Handheld drifts, a refocus hunt, a late pan. Never smooth, never a drone, never CGI-clean. SUBJECT: ordinary six-storey 1970s apartment block — pale yellow-cream render, concrete balconies two sides, standard windows, a small shopfront with an awning on the ground floor, washing lines with laundry. Residents on the balconies, period clothing, calm, leaning on railings watching the ground come up. Beneath the flat concrete underside a single intense rocket landing plume — focused white-orange flame with visible shock diamonds, like an orbital booster landing burn. No legs, no fins, no machinery. It descends on the flame. CROWD: a few dozen ordinary people, all ages, 1970s summer clothes — patterned dresses, short-sleeved shirts, high-waisted trousers — on a wide concrete apron, seen from behind, looking up. Period cars at the edges. Curious and excited, never frightened, never fleeing. PHYSICS: enormous real mass. Slow descent, smooth deceleration. Exhaust blasts a huge rolling dust cloud on contact. Real flame, real dust, real weight. AUDIO: distant compressed rocket roar on a single microphone, building. Bass rumble through the ground. Dust crackle. At touchdown the engine cuts dead — one full second of near silence, only wind. Then applause, whistles, cheering, a car horn. No music, no narration, no score. SHOT 1 | 0.0-3.0s. Extreme long lens, high in a hazy pale sky. The apartment block descends slowly, upright and level, plume burning beneath, heat distortion. Camera drifts and corrects. Tiny figures on the balconies. SHOT 2 | 3.0-6.0s. HARD CUT to ground level, behind the crowd. Dozens from behind, shielding eyes, some pointing. The building comes down into frame, growing, roar building. Period cars and low buildings at the edges. SHOT 3 | 6.0-9.0s. The plume strikes the concrete apron. Enormous dust cloud rolls toward camera. Crowd braces, clothes and hair blown back, a few turning faces away, one hat lifting. Building fills the upper half, still descending. SHOT 4 | 9.0-12.0s. Through thinning dust the building settles onto the concrete, takes its weight with a deep shudder. Plume cuts out instantly. Silent and still. Dust hangs. Nobody moves. SHOT 5 | 12.0-15.0s. Dust clears. The block stands ordinary, as if it had always been there — laundry still hanging, gently swaying. One long beat of stillness. Then the crowd bursts into applause, arms up, residents on balconies wave back. Final: the building among the applauding crowd, dust settling, laundry swaying, faded 1970s film colour. Hold. NEGATIVE: no text, no captions, no logos, no brand names, no company markings, no readable signage. No modern clothing, no smartphones, no modern cars, no drone, no gimbal, no CGI gloss. No fire damage, no explosion, no collapse, no debris striking anyone, no injuries, no panic, no one running. Building never tilts, never wobbles, never falls. No landing legs, no fins, no visible rocket nozzles.

1 step1051K
Kling 3.015s · 16:9
Inspired by Xaroon_xon X

30-second 4:3 photoreal fantasy cinematic. @image1 is the rider’s face. @image2 is the storyboard — photocopy outfit, AMULET, and DRAGON from the board. Not sci-fi, not a spacecraft, not an EVA suit. Use they / their / them only. 0–3s: Extreme wide over a sea of clouds, sunrise. Camera through volumetric cloud. Tiny falling figure. 3–6s: They fall toward camera, rotate, stabilize. Face readable. 6–11s: Hands to chest, inspect a gold amulet, activate it, core glows. Light on their face. 11–16s: A gigantic dragon unfolds behind them in the clouds. Wings spread. Low-angle the dragon passes overhead. 16–22s: They sit at the dragon’s neck, flying. Clouds race. 22–27s: Dragon banks through snow-capped peaks at speed. 27–30s: Pull wide to sunset over the cloud ocean. Hold. No on-screen text. AUDIO: wind, wingbeats, amulet chime, no lyrics.

3 steps21614.8K
Seedance 2.530s · 4:3
Living Gaze

CHARACTER LOCK — HIGHEST PRIORITY: the person is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions. Preserve their gender presentation exactly as shown. Keep the black round glasses from @image1 on their face in every second. Do not beautify, slim, de-age, restyle them, or remove the glasses. No other people in frame. Use they / their / them only. ATTACHED IMAGE IS MANDATORY AND FINAL: wherever the reference and this text disagree, follow the image. @image1 is the person. Photocopy the face, the high bun with loose wisps, the glasses, and the light beige/taupe crew-neck top. Do not invent a different hair colour, a different eye colour, or a different neckline. 9:16. TOTAL DURATION: 10 SECONDS. OPENING: already an extreme close-up of the live face. Never the studio still, never a grey headshot as frame 0. 0-2s: Extreme close-up, face filling 90-100% of frame. Eyes fully open, staring into lens. Calm, composed, subtly warm. Head still, lips relaxed, tiny natural eye movement. Focus on the eyes. Glasses stay on. 2-5s: Upper eyelids slowly lower to half-lidded — not a blink, a gradual, natural movement. Eyebrows still, mouth closed, no head rotation. Emphasize eyelashes, eyelid texture, under-eye skin, nose bridge, natural lip moisture, pores and skin texture. Glasses stay on. 5-7s: They slowly reopen their eyes, returning to a calm, warm gaze. Camera slowly pulls back. 7-10s: Pull back to reveal the full head, hair exactly as shown in @image1 (high bun, loose wisps), ears and the beige/taupe crew-neck neckline, ending in a frontal head-and-shoulders portrait. They face the lens throughout, lips closed, ending with the faintest natural smile — warm and approachable, not a full grin. Hair stays natural with subtle forehead-wisp movement. Final second holds eye contact. Glasses stay on. 85-105mm lens, eye-level frontal camera, no wide-angle distortion. Moderate depth of field; eyes, nose and lips stay clear. Live-action realism: preserve pores, skin texture and natural imperfections — avoid flawless/airbrushed skin. No subtitles. No on-screen text or watermark.

2 steps
MiniMax H310s · 9:16
Inspired by AIwithMinalon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. An exactly 15-second ultra-realistic cinematic dance performance film, 16:9. Hard cuts. Photoreal music-video. @image1 is the lead. Preserve her face exactly. High tight bun, long dark hair. Do not recast. @image2 is her wardrobe. Structured white strapless fashion top, dark navy high-waisted baggy jeans, black boots, chunky silver hoops. Same look every shot. Fully clothed. SET: underground parking garage. Board-formed concrete, low ceiling, fluorescent strips, wet polished floor. Two muscle coupes left and right as gateposts. One car at the back, headlights ON into the lens. LIGHT: backlit. Headlights plus two hard beams through haze, a V converging on the lead. Rim-lit, cool concrete, warm tungsten. Wet floor mirrors beams. CREW: eight dancers, mixed, exact unison, black leather jackets, black tops, wide light-wash jeans, combat boots. Left mirrors right. Faces not featured. Every wide shot centred, symmetrical, one-point. Vanishing point behind the lead. AUDIO: no music, no dialogue. Boots on wet concrete, fabric, breathing, car idle, garage echo. [0.0-2.5s] Wide, eye level, locked. Lead far back centre, small, rim-lit. Eight dancers a tight wedge, bent low, heads down, still. Beams a V at her. Only haze moves. [2.5-5.0s] Camera pulls back and lowers. Lead walks forward. Dancers break into two mirrored groups, low and heavy, arms sweeping. [5.0-6.5s] Low close. Lead large centre, walking toward lens, hands on hips. Two dancers at the left and right edges, arms out, framing her. [6.5-7.5s] HARD CUT. Beauty close-up, three-quarter profile, long lens, background dissolved. Hoop earring catches light. Jaw set. She does not look at camera. [7.5-8.3s] HARD CUT. Low wide. Lead centre mid-move, crew braced, unison. [8.3-9.5s] HARD CUT. Close-up of one black combat boot on wet concrete, laces sharp, rim light. [9.5-13.0s] HARD CUT. Extreme low angle on the floor, tilted up. Lead in a low dance move, crew around her, arms driving, mirrored. Wet floor reflections. [13.0-15.0s] HARD CUT back to first framing. Lead centre, both arms raised in a V. Eight dancers bowed at the waist in two mirrored lines. Starburst headlights. Hold. NEGATIVE: on-screen text, logos, brand names, music, extra limbs, face drift, changing clothes, looking into the lens, rain, fire, broken symmetry.

4 steps17730
Seedance 2.015s · 16:9
Photo Waking

CHARACTER LOCK — HIGHEST PRIORITY: PERSON_A is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and colour, eyebrows, nose, lips, skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions. Preserve their gender presentation exactly as shown. PERSON_B, once animated, is exactly the person shown in @image2 — their exact facial features, apparent age as the photo shows, skin tone, hair and expression range. Do not beautify, de-age, age up, or restyle either person. No other people enter the scene. Whenever this text and either reference image disagree, follow the image. @image1 is PERSON_A, present-day — photocopy face, hair and the navy square-neck look from the still. @image2 is the old photograph containing PERSON_B. PERSON_B’s identity comes only from that photo. RESTRAINED PHOTO-WAKING RULE: PERSON_B begins completely still, exactly as printed in @image2 — aged photo texture, tone and grain visible. Their first movements are small and natural only: a soft blink, a faint warm smile, gentle breathing, the smallest head tilt. Do not give PERSON_B fast or large head turns or exaggerated motion before they have fully stepped out of the photo plane — abrupt motion on a photographic likeness distorts the face. Only after they have visibly left the frame do they move naturally and fully. 16:9. TOTAL DURATION: 12 SECONDS. OPENING: already in the room with PERSON_A and the framed print. Never a studio headshot as frame 0. 0-3s: Static establishing shot. PERSON_A stands or sits calmly, holding or seated beside a framed print of the old photo showing PERSON_B — visibly aged, grain, faded tone, slightly worn paper texture. Quiet, still, a little anticipatory. Camera holds completely still. Natural indoor or soft outdoor lighting that makes both PERSON_A and the framed photo look like they belong in the same room. 3-6s: Inside the frame, PERSON_B gently comes to life — a soft blink, a faint warm smile forming, gentle breathing, the smallest natural head tilt. The old photo’s color and depth slowly warm and deepen, the flat printed texture gradually giving way to living dimension, without changing PERSON_B’s identity, age or appearance. PERSON_A notices, their expression shifting to quiet wonder. 6-10s: PERSON_B steps out of the photo’s plane into PERSON_A’s space. They close the distance and share a warm, gentle hug, arms wrapping around each other’s backs. Both have joyful, emotional expressions, eyes slightly teary. Soft happy laughter, no dialogue needed. 10-12s: Both settle into the embrace. Warm, natural expressions on both faces. Camera slowly pushes in a few inches, or holds steady. CINEMATIC STYLE: Soft natural or warm indoor light, gentle handheld micro-movement, shallow depth of field, live-action realism — preserve real skin texture and imperfections on PERSON_A; PERSON_B’s texture may echo the photo’s grain slightly even once alive, as a subtle visual signature that they came from the photograph. No subtitles. No on-screen text or watermark. Hands have five fingers each, anatomically correct.

3 steps
MiniMax H312s · 16:9
Inspired by Noor_ul_ain43on X

13-second 16:9 ultra-realistic cinematic fight in a messy urban apartment/studio: books, posters, scattered furniture, warm lamps, cool daylight through large windows. @image1 is absolute character truth for person 1. @image2 is absolute character truth for person 2. Photocopy both sheets. Do not describe appearance. Use they / their / them only. 0–2s: Wide establishing the whole room. @image1 swings a long wooden object. @image2 blocks and dodges. 2–8s: Fast believable choreography — blocks, punches, grapples, shoves. Handheld, wide / medium / low / impact close-ups. Camera shake, motion blur, both faces readable. 8–11s: A powerful takedown. One of them hits the floor. 11–13s: The other remains standing in the foreground, breathing, defensive stance. Dramatic hold. Room stays the same. No cartoon physics. No on-screen text. AUDIO: impacts, breath, room tone, no lyrics.

5 steps481K
Seedance 2.013s · 16:9
Inspired by Coinis AIon organic

Photoreal cinematic lifestyle shopping commercial, warm natural light, premium grade, horizontal. Lead is @image1 (identity locked, exact face/hair, two hands). Hero product is exactly @image2 (same shape/colour/details, never changing). @image1 stays fully dressed in a complete neutral everyday outfit with ordinary closed shoes on at all times, never barefoot; whatever @image2 is — a top, jacket, trousers, bag, shoes or accessory — it is added onto that complete outfit while every other garment and both shoes stay on and neutral. 0-4s home: @image1 with mug + smartphone. 4-8s over-shoulder: phone shows a clean shopping app with the @image2 product, thumb taps buy. 8-12s macro beauty shot of the @image2 product rotating. 12-16s @image1 opens a parcel and lifts out the exact @image2 product. 16-20s @image1 puts on or uses @image2 at a mirror, fully dressed with shoes on, satisfied. 20-26s @image1 walks a city street with @image2, phone in hand, three-quarter angle, tracking dolly, wearing the complete outfit and shoes. 26-30s confident final beat holding on @image1 with @image2. Let each beat play out fully and finish its action before the next; ONE continuous coherent commercial, smooth motivated transitions, no abrupt cut to an unrelated or random scene mid-action; @image1 identity consistent; @image2 identical every shot. Realistic fabric and small-object physics, exactly two hands. SOUND: upbeat warm commercial music bed + soft foley (mug, tap, parcel rustle, footsteps, city ambience); no spoken dialogue, no invented language. Negative: product not matching @image2 or its colour/shape changing; @image1 identity, face or hair changing; a third hand, extra arm, more than two hands, extra or missing fingers; bare feet, barefoot, missing or a single shoe, partially undressed, or wearing only the product with nothing else; describing other garments in words beyond the outfit and footwear lock; on-screen captions, subtitles or watermark; a scene cutting off mid-action or jumping to a random unrelated scene; any character vanishing, dissolving, fading or teleporting into thin air — every exit is physical; plastic or airbrushed skin.

2 steps
Seedance 2.530s · 16:9
Inspired by Mohidxaion X

@image1 is ELARA — photocopy her exact face, bone structure, silver-grey wavy hair, brown eyes. IGNORE any bomber, tank, shorts, or boots in @image1. Identity only. WARDROBE FROM THE RECIPE, NOT THE STILL: Soft pastel-pink ribbed pajama camisole with lace trim and a small ribbon at the neckline, loose oatmeal-cream knit cardigan slipping off one shoulder to the cami strap. Small gold hoop earrings, thin gold coin necklace. Bare face, night routine. @image2 is the JAR. Photocopy this product exactly: squat round frosted aqua-blue jar, matte white screw lid, white label with SKINTIFIC, 5X CERAMIDE, BARRIER MOISTURE GEL, Hyaluronic Acid / Centella / Marine Collagen, 30g / 1 FL.OZ. Same silhouette, same aqua body, same white lid. Inside: a glossy translucent-white moisture GEL. NEVER a white CeraVe jar. NEVER a purple diagonal panel. NEVER Chanel. ONE PERSON. 9:16 vertical TikTok. No on-screen captions. No extra logos. 15-second ultra-photorealistic UGC skincare clip. Phone propped on a bedroom vanity at night, then handheld. She talks to camera like a friend. Propped-phone wobble, autofocus hunt. LOCATION: cozy bedroom vanity, lilac-grey wall, ribbed white vase with dried lavender, round mirror edge, lilac waffle towel, water tumbler, rumpled white linen bed, warm bedside lamp. LIGHT: warm 3000K lamp from frame-left, cool dusky lilac fill from the right. No ring light. VOICE: soft, warm, slightly breathy American, unhurried. Exact lines, in order, lip-sync. [TIMELINE — 15 SECONDS, 9:16] 0–4s HOOK: Mid-motion. ELARA leans into the propped phone, cheek to the lamp, then lifts the @image2 aqua jar beside her face, lid on, label toward camera. Raised-brow, tiny proud smile. Dialogue: "The reason I wake up with skin like this? It's literally this jar." 4–8s WHY: Twists the white lid off, tilts the jar so SKINTIFIC / 5X CERAMIDE / BARRIER MOISTURE GEL is sharp. Taps the label casually. Dialogue: "Five ceramides, hyaluronic acid, centella and marine collagen. It works the night shift so I don't have to." 8–12s TEXTURE: Handheld 9:16 selfie, close. Two fingertips scoop the glossy gel, a clean peak. Dots cheek, forehead, chin, presses outward. Gel goes sheer. Rubs fingertips — nothing left. Dialogue: "It's thick, but watch.. it just melts. Zero greasy feeling." 12–15s CTA: Phone back on the vanity a little crooked. Chin on hand. Jar soft-focus lower in frame, aqua + white lid readable. Sleepy half-smile, tiny nod. Reaches to stop recording, frame jolts. Dialogue: "Save this for tonight. Morning you will thank me." Audio: her lines + room tone, lid click, jar on vanity. No music.

3 steps18849.8K
Seedance 2.515s · 9:16
Garden WakeMiniMax H3 · 16:9 · 12sRecreate workflow